Enhancing task-oriented robotic grasping via 3D affordance grounding from vision-language models
Abstract Existing task-oriented grasping approaches often rely on 2D pixel-wise affordance segmentation or predefined part annotations, limiting their applicability in unstructured 3D environments and constraining the grasp planning space. To overcome these limitations, we introduce a novel affordan...
Tallennettuna:
| Päätekijät: | , , , , |
|---|---|
| Aineistotyyppi: | Artigo |
| Kieli: | Inglês |
| Julkaistu: |
Springer
2025-12-01
|
| Sarja: | Complex & Intelligent Systems |
| Aiheet: | |
| Linkit: | https://doi.org/10.1007/s40747-025-02169-0 |
| Tagit: |
Ei tageja, Lisää ensimmäinen tagi!
|